Self-Supervised Transfer Learning from Natural Images for Sound Classification
We propose the implementation of transfer learning from natural images to audio-based images using self-supervised learning schemes. Through self-supervised learning, convolutional neural networks (CNNs) can learn the general representation of natural images without labels. In this study, a convolut...
Main Authors: | Sungho Shin, Jongwon Kim, Yeonguk Yu, Seongju Lee, Kyoobin Lee |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/7/3043 |
Similar Items
-
BattleSound: A Game Sound Benchmark for the Sound-Specific Feedback Generation in a Battle Game
by: Sungho Shin, et al.
Published: (2023-01-01) -
Semi-Supervised NMF-CNN for Sound Event Detection
by: Teck Kai Chan, et al.
Published: (2021-01-01) -
Weakly Supervised U-Net with Limited Upsampling for Sound Event Detection
by: Sangwon Lee, et al.
Published: (2023-06-01) -
Transfer learning application of self-supervised learning in ARPES
by: Sandy Adhitia Ekahana, et al.
Published: (2023-01-01) -
From Self-supervised Learning to Transfer Learning with Musculoskeletal Radiographs
by: Hinterwimmer Florian, et al.
Published: (2022-09-01)